- Download Telegram App on phone and register
- Download Telegram Desktop App on computer and login
- Open a terminal
# install Ollama
curl -fsSL https://ollama.com/install.sh | sh # for Linux
You will see this:
"Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
>>> The Ollama API is now available at 127.0.0.1:11434."
You can copy the address and open it on your browser to check Ollama running status.
# Pull the desired model
Ollama pull qwen3-vl:8b # replace with your model
# Check the model list
Ollama ls
# install Nanobot (stable version)
pip install nanobot-ai
# Initialize
nanobot onboard
# configuration file
sudo nano ~/.nanobot/config.json
# Paste the following content in the config.json file:
{
"providers": {
"openai": {
"apiKey": "dummy",
"apiBase": "http://localhost:11434/v1"
}
},
"agents": {
"defaults": {
"model": "qwen3-vl:8b" # your model here
}
},
"channels": {
"telegram": {
"enabled": true,
"token": "YOUR_BOT_TOKEN_HERE",
"allowFrom": ["YOUR_NUMERIC_USER_ID_HERE"]
}
},
"tools": {
"web": {
"search": {
"apiKey": "your-brave-search-api-key",
"maxResults": 5
}
},
"exec": {
"timeout": 60
},
"restrictToWorkspace": false,
"mcpServers": {}
}
}
# Test agent
nanobot agent -m "Hi"
# Start gateway
nanobot gateway
4. Test it on telegram and enjoy using your Nanobot assistant
